Triple

T13871538
Position Surface form Disambiguated ID Type / Status
Subject Back Cove (Portland, Maine) E333462 entity
Predicate locatedIn P40 FINISHED
Object Maine E29256 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Maine | Statement: [Back Cove (Portland, Maine), locatedIn, Maine]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maine
Context triple: [Back Cove (Portland, Maine), locatedIn, Maine]
  • A. Maine chosen
    Maine is a northeastern U.S. state known for its rugged coastline, maritime history, and vast forested interior.
  • B. Maine
    Maine is a historical region in northwestern France that played a significant role in the medieval power struggles between the English and French crowns.
  • C. New Hampshire and Maine
    New Hampshire and Maine are neighboring New England states in the northeastern United States, known for their rugged coastlines, forested landscapes, and historic colonial towns.
  • D. Freedom, Maine
    Freedom, Maine is a small rural town in central Maine known for its scenic countryside and tight-knit community.
  • E. New Hampshire
    New Hampshire is a small New England state in the northeastern United States known for its mountainous landscapes, early presidential primary, and “Live Free or Die” motto.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d81c5ced9c8190b0e9bcc6effe5959 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de05c638248190bbe5d19f7b88d0f9 completed April 14, 2026, 9:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c6fb2b708190ae6e36bfb93f8bdd completed May 3, 2026, 10:06 p.m.
Created at: April 9, 2026, 10:14 p.m.